One AI Assistant Configuration Guide

Introduction

The One AI Assistant Configuration Guide outlines how to set up and manage access to One AI Assistant. Proper configuration ensures accurate, relevant outputs and helps you maintain secure control over who can use the tool. This guide covers permission settings, example prompt customization, and vector configurations to help you tailor One AI Assistant to your organization’s needs.

Permissioning One AI Assistant

To access One AI Assistant, connect with your Customer Success Lead to discuss enablement options for this feature. One Model team, here is a link to the initial internal enablement instructions.

Once One AI Assistant has been enabled by your CS team, there are a number of configuration options available.

Access to One AI Assistant is controlled by a set of permissions that determine what users can see and do. These include features like Answers, Insights, Visualizations, and Storyboard Navigation. You can combine these permissions to give different users the right level of access based on their role. To learn more about these permissions—and how they fit into broader role-based access across One Model—see the One AI Generative AI section in our One Model Roles and Permissions reference guide.

Controlling Access to One AI Assistant

Access to One AI Assistant is managed through the Application Access Role permission CanAccessOneAIAssistant. Users must have this permission to see or use the Assistant.

Controlling Access to Configure the One AI Assistant

The ability to configure One AI Assistant is controlled by the CanConfigureOneAI permission. This is typically reserved for site administrators, as it allows access to all Assistant configuration settings.

Configuring One AI Assistant

Enabling permission to One AI Assistant is just the first step—users won’t be able to use it until the Assistant is properly configured. Configuration determines which data the Assistant can reference and how it interacts with users. Users with the CanConfigureOneAI permission will see a One AI Configuration option in the Admin menu. Selecting it opens a screen with five core areas to configure:

1. General One AI Assistant Settings

   These global settings control the Assistant's default behavior and visual layout. You can:

   • Customize the intro text shown above the input box 

   • Choose whether the query pane is expanded by default

   • Decide when to display filters/selections above charts and tables 

   These settings apply to all users and help create a guided, branded, or simplified experience.

   General One AI Assistant Settings configuration via One AI Configuration

2. Example Prompts Configuration

   Example prompts appear on the Assistant's landing screen to help users get started. You can customize these prompts to reflect your organization's most common questions, themes, or preferred phrasing. Each prompt can include an icon for its associated feature or visualization type image. Prompts can also be reordered by dragging and dropping: click and hold the numbered prompt header (for example, Example Prompt 1), move it to the desired position, and release. After you click Save, the new order will be applied for all users.

   Example Prompts configuration via One AI Configuration

3. Answers - Topic Configuration

   Topics allow you to group related questions in the Answers experience. These are user-defined categories like “Recruitment,” “Learning,” or “Site Usage” that help organize curated content.Answers - Topic configuration via One AI Configuration

4. Answers - Question Configuration

   This section allows you to define specific questions and link them to existing content by assigning a topic, a storyboard, a page within that storyboard, and a specific chart or tile. These curated questions appear in the Answers experience and help guide users directly to the most relevant visuals.Answers - Question configuration via One AI Configuration

5. Vector Configuration

   Vector configuration defines what content the Assistant can use when interpreting user prompts in the Visualizations and Storyboard Navigation tools. Metrics and dimensions are used in chart-based queries, while storyboards determine where the Assistant can navigate when users ask to explore existing content. The Assistant also uses dimension node values (e.g., “Chicago,” “Level 3”) to support filtering. Avoid including dimensions with PII in their nodes, such as employee names. This configuration works in combination with data access roles. If a user doesn’t have access to a metric or dimension—even if it’s configured in the Assistant—they won’t be able to query it. Likewise, if a user does have access, but the Assistant hasn’t been configured to include that metric or dimension, it won’t be available in the Assistant. For example, if the Gender dimension is enabled in the Assistant’s configuration but a user’s data access role does not permit access to the Gender dimension, that user will not be able to build queries using it in One AI Assistant.

Vector configuration via One AI Configuration

Vector Configuration Best Practices

Because One AI Assistant relies on a large language model (LLM) and a vector database to interpret prompts and match them with your data, thoughtful configuration is essential for accurate, relevant results.

1. Be deliberate in configuration: When configuring One AI Assistant, site administrators should carefully select which metrics and dimensions the assistant can access. Striking a balance is key—include enough data to support meaningful and interesting queries, but avoid overwhelming the assistant with similarly named metrics, dimensions, and dimension nodes. If a metric or dimension is rarely used or only relevant to a small group, it may not need to be included. Focus on metrics and dimensions that are widely relevant and useful, and avoid overloading the assistant with similar options like multiple "headcount" or "termination" metrics. This ensures the assistant can efficiently find and return the right data.
2. Exclude "Previous" dimensions: "Previous" dimensions (e.g., previous location, previous performance rating) are typically used for internal movement metrics, like transfers or promotions, and don’t apply to most other types of queries. If this applies to your One Model instance, consider excluding these dimensions from your One AI Assistant configuration since these dimensions contain the same nodes as their “Current” counterparts. This helps avoid confusion and irrelevant outputs, especially for casual users who may not fully understand the specific data requirements needed for these dimensions.
3. Avoid including multiple dimensions with similar nodes: Be mindful when configuring dimensions that have the same or very similar nodes (e.g., "work location" and "home location" both containing "Chicago"). If multiple dimensions share identical nodes, One AI Assistant may struggle to determine which one to use when you query data (e.g., "show me headcount over the last 12 months in Chicago"). To prevent confusion and inaccurate results, only include one relevant dimension, unless you are prepared to make minor edits in the query builder.
4. Exclude metrics and dimensions built for One AI predictive model storyboards: Avoid including metrics and dimensions that were built specifically for One AI predictive model storyboards. Since there’s currently no way to track the machine learning model's performance, when it was last run, or how these metrics interact with other data on the site, including them may result in inaccurate or misleading outputs. 
5. Exclude metrics that can be reached with dimension filters: If a metric can be reached using a dimension filter, don’t include it as a separate metric. This reduces the number of similarly named metrics and helps One AI Assistant return accurate results. For instance, instead of including a separate "Headcount - Female" metric, use the standard "Headcount (EOP)" metric and apply a gender filter for women. These metrics are typically included in order to calculate other metrics, such as “Headcount % - Female”. These calculated metrics are okay to include. 
6. Provide clear metric definitions for user clarity: Ensure that metric definitions are clear and easy to understand. These can be edited in the metric editor and are important because when users drill through a data point, the metric definition is also displayed. This helps more casual users verify that One AI Assistant is using the correct metric for their query, giving them confidence in the results. Additionally, admins can download all metric definitions from the ‘Metrics’ admin report to provide a "metric dictionary" for users who don’t have drill-through access, ensuring everyone has a reference to the metrics used.
7. Consider excluding metrics and dimensions that contain PII: Metrics and dimensions that include personally identifiable information (PII) in their titles or nodes—such as employee names—typically don’t add value for One AI Assistant and may not be appropriate for inclusion. While OpenAI never trains on your data, the metadata used to configure the assistant (including embeddings of metric and dimension names and dimension node values) is sent to OpenAI whenever configuration is updated or the site reprocesses. For organizations with strict data governance policies, it may be worth considering whether to exclude PII-labeled items to avoid unnecessary exposure.

Conclusion

This guide covers how to set up One AI Assistant and maintain it over time. With the right permissions, prompt setup, and configuration choices, your team can use the Assistant securely and effectively. This ensures accurate, relevant results and a smooth user experience.